2010
DOI: 10.1016/j.ejor.2009.11.003
|View full text |Cite
|
Sign up to set email alerts
|

Evolutionary optimisation of noisy multi-objective problems using confidence-based dynamic resampling

Abstract: Evolutionary optimisation of noisy multi-objective problems using confidence-based dynamic resampling. European Journal of Operational AbstractMany real-world optimisation problems approached by evolutionary algorithms are subject to noise. When noise is present, the evolutionary selection process may become unstable and the convergence of the optimisation adversely affected. In this paper, we present a new technique that efficiently deals with noise in multi-objective optimisation. This technique aims at pre… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
42
0

Year Published

2012
2012
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 55 publications
(42 citation statements)
references
References 30 publications
0
42
0
Order By: Relevance
“…Simulation-based optimization (SBO) is an attractive approach to address this problem, for it can accurately capture the inherent uncertainty and complexity of the manufacturing system, while searching for near-optimal solutions for the problem analysed [21,46,20]. The SBO model consists of a simulation model and an EA coupled in a black-box fashion.…”
Section: Simulation-based Optimization Modelmentioning
confidence: 99%
“…Simulation-based optimization (SBO) is an attractive approach to address this problem, for it can accurately capture the inherent uncertainty and complexity of the manufacturing system, while searching for near-optimal solutions for the problem analysed [21,46,20]. The SBO model consists of a simulation model and an EA coupled in a black-box fashion.…”
Section: Simulation-based Optimization Modelmentioning
confidence: 99%
“…In Section VI we evaluate our new optimiser along with four other recent noise-tolerant MOEAs [6], [16], [21], [22], on standard test problems modified by the addition of noise. In particular we show that our proposed optimiser performs well in the presence of noise with a wide range of characteristics, including when the noise varies spatially and temporally during the course of the optimisation.…”
Section: Introductionmentioning
confidence: 99%
“…However, it was not until the early 2000s that a significant number of multi-objective optimisers began to be developed specifically to tackle uncertain optimisation [12], [13], [14], [5], [6], [15], [7], [16], [17], [18], [19], [20], [21], [22], [23]. Typically uncertainty is modelled as noise added to the function evaluations, although recent work has begun looking at the situation where the objective functions themselves are uncertain [24].…”
Section: Introductionmentioning
confidence: 99%
“…The problems developed in these studies are deterministic functions that demonstrate differences between the nominal Pareto front and the 'robust' front. Similarly, Goh and Tan [9], Knowles and Corne [12], Syberfeldt et al [18] and Fieldsend and Everson [5] used deterministic test problems with added noise to the objective values to benchmark their algorithms. This type of problem is sufficient for the assumption that the 'true' objective vector is masked by measurement noise.…”
Section: Introductionmentioning
confidence: 99%
“…Typically, in these studies, symmetric random noise is added to the decision variables [3,7,14,15,16] or the objective functions [5,9,12,18] in a bespoke way that meets the requirements for the specific uncertainties and definitions of robustness being considered. The problem that is used to benchmark every suggested algorithm is tailored to the type of uncertainty and definition of robustness considered in the study.…”
Section: Introductionmentioning
confidence: 99%